EP4113527A1 - Adjustment of medicament delivery by a medicament delivery device based on menstrual cycle phase - Google Patents
Adjustment of medicament delivery by a medicament delivery device based on menstrual cycle phase Download PDFInfo
- Publication number
- EP4113527A1 EP4113527A1 EP22181777.8A EP22181777A EP4113527A1 EP 4113527 A1 EP4113527 A1 EP 4113527A1 EP 22181777 A EP22181777 A EP 22181777A EP 4113527 A1 EP4113527 A1 EP 4113527A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- user
- menstrual cycle
- insulin
- phase
- delivery device
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M5/00—Devices for bringing media into the body in a subcutaneous, intra-vascular or intramuscular way; Accessories therefor, e.g. filling or cleaning devices, arm-rests
- A61M5/14—Infusion devices, e.g. infusing by gravity; Blood infusion; Accessories therefor
- A61M5/168—Means for controlling media flow to the body or for metering media to the body, e.g. drip meters, counters ; Monitoring media flow to the body
- A61M5/172—Means for controlling media flow to the body or for metering media to the body, e.g. drip meters, counters ; Monitoring media flow to the body electrical or electronic
- A61M5/1723—Means for controlling media flow to the body or for metering media to the body, e.g. drip meters, counters ; Monitoring media flow to the body electrical or electronic using feedback of body parameters, e.g. blood-sugar, pressure
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B10/00—Other methods or instruments for diagnosis, e.g. instruments for taking a cell sample, for biopsy, for vaccination diagnosis; Sex determination; Ovulation-period determination; Throat striking implements
- A61B10/0012—Ovulation-period determination
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
- G16H20/17—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients delivered via infusion or injection
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
- G16H40/63—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for local operation
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
- G16H40/67—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for remote operation
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M2205/00—General characteristics of the apparatus
- A61M2205/33—Controlling, regulating or measuring
- A61M2205/3303—Using a biosensor
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M2205/00—General characteristics of the apparatus
- A61M2205/50—General characteristics of the apparatus with microprocessors or computers
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M2230/00—Measuring parameters of the user
- A61M2230/04—Heartbeat characteristics, e.g. ECG, blood pressure modulation
- A61M2230/06—Heartbeat rate only
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M2230/00—Measuring parameters of the user
- A61M2230/20—Blood composition characteristics
- A61M2230/201—Glucose concentration
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M2230/00—Measuring parameters of the user
- A61M2230/50—Temperature
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M2230/00—Measuring parameters of the user
- A61M2230/63—Motion, e.g. physical activity
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M2230/00—Measuring parameters of the user
- A61M2230/65—Impedance, e.g. conductivity, capacity
Definitions
- a conventional medicament delivery device may deliver medicament at basal dosages and/or bolus dosages.
- the basal dosages are delivered on an-ongoing basis and aim to address a substantial portion of the need for the medicament on an on-going basis.
- the bolus dosages are delivered when requested by a user or when the control system for the medicament delivery device concludes based on information regarding the user that there is a need to deliver the bolus dosage.
- the basal dosages are delivered automatically by the medicament delivery device to the user.
- the control system is generally responsible for determining the timing and the dosages for such medicament deliveries.
- TDI total daily insulin
- the conventional insulin delivery device may calculate a basal dosage based on total daily insulin (TDI).
- TDI represents the aggregate amount of insulin needed by the user for a day.
- TDI is typically calculated based on the weight of the user.
- a commonly used formula is that TDI equals user weight in pounds divided by 4.
- the TDI for a 200-pound man is 200 divided by 4 or 50 units of insulin.
- the basal dosage is conventionally determined to be one half of TDI.
- Insulin boluses are typically delivered in response to meals by the user.
- the meals will increase the user's blood glucose concentration.
- the magnitude of the increase in blood glucose concentration is related to the quantity of carbohydrates ingested.
- a conventional insulin delivery device may determine what dosage of insulin will compensate for the quantity of carbohydrates ingested.
- the conventional insulin delivery system may multiply the carbohydrates ingested by the insulin to carbohydrates ratio (ICR).
- the ICR conventionally may be set as a value typically selected from the range of 4 to 50. For example, a value of 4 for the ICR implies that 1 unit of insulin is to be delivered for every 4 grams of carbohydrates ingested.
- the conventional insulin delivery system may also look at the current blood glucose concentration and the insulin on board (IOB) for the user, which represents the quantity of insulin delivered to user that still has insulin action remaining.
- ICR insulin to carbohydrates ratio
- a method is performed by a processor in an electronic device.
- the method includes receiving information regarding a menstrual cycle of a user and based on the received information regarding a menstrual cycle of a user, adjusting a medicament dosage to be delivered by an automated medicament delivery device.
- the received information may be a current phase of a menstrual cycle of the user.
- the received information may be received from a machine learning model.
- the received information may be information from which a current phase of the menstrual cycle is determined.
- the received information may include information from one or more sensors secured to the user.
- the medicament may be one of insulin, glucagon or a glucagon peptide-1 (GLP-1) agonist.
- the adjusting may include adjusting an insulin dosage to be delivered by the automated medicament delivery device based on an insulin sensitivity of the user for a current phase of the menstrual cycle of the user.
- a method is performed by a processor in an electronic device.
- the method includes receiving input from a sensor. Based at least in part on the received input, a phase of a menstrual cycle of a user is determined with the processor.
- the method also includes determining insulin sensitivity of the user with the processor based on the determined phase of the menstrual cycle and adjusting the insulin delivered by a delivery device based on the determined insulin sensitivity.
- the sensor may sense skin temperature, heart rate, skin conductance, or activity level.
- the method may further include receiving additional inputs from multiple sensors and using the additional inputs in the determining of the phase of the menstrual cycle of the user.
- the additional inputs from the multiple sensors may include a blood glucose concentration value for the user from one of the sensors that is a glucose monitor.
- the adjusting may adjust a size of a dosage of basal insulin to be delivered by the delivery device.
- the adjusting may adjust a size of dosage of an insulin bolus to be delivered by the delivery device.
- a method is performed by a processor in an electronic device. Per the method, patterns of medicament sensitivity of a user based on a phase of a menstrual cycle of a user are learned by a machine learning model executing on the processor. Delivery of medicament to the user are adjusted by the processor based on the learned patterns to be delivered by a medicament delivery device to the user.
- the method may further include receiving input from at least one sensor that senses information regarding the user and processing the input to determine a current phase of the menstrual cycle of the user.
- the input may include heart rate and skin temperature.
- the input may include blood glucose concentration and an indication of activity level.
- the learning may include training on a data set derived from women other than the user and subsequent to the training on the data set, training on data from the user to customize the machine learning model to the user.
- the medicament may be one of insulin, glucagon or a glucagon peptide-1 (GLP-1) agonist, for example.
- the true medicament dosage needs of a user may vary from user to user. Moreover, the true medicament needs of a given user may vary over ranges of days or weeks and may vary even during a single day.
- conventional medicament delivery devices do not account for many of these variations in medicament dosage needs.
- a user's medicament dosage needs may vary based on the menstrual cycle of the user.
- insulin sensitivity of a user may vary over the course of the menstrual cycle.
- Conventional insulin delivery devices do not account for this variation in insulin sensitivity due to the menstrual cycle phase of the user. This can be problematic in that the insulin needs of the user change over the course of the menstrual cycle of the user, but the conventional insulin delivery devices do not adjust for the change. As a result, the user may be at greater risk of hyperglycemia or hypoglycemia.
- Exemplary embodiments described herein account for the differing needs of the user over the menstrual cycle of the user to better control the blood glucose concentration of the user.
- the exemplary embodiments may be realized in control systems for medicament delivery devices that deliver medicaments, such as medicaments that regulate blood glucose concentration levels. Examples of such medicaments that regulate blood glucose concentration levels include insulin, glucagon, and glucagon peptide-1 (GLP-1) agonists.
- the exemplary embodiments are able to better tailor the dosages of the medicament delivered to the user with the medicament delivery device to reduce the risk of hyperglycemia and hypoglycemia and help reduce blood glucose concentration excursions.
- Some exemplary embodiments may use sensors, such as sensors of heart rate, skin temperature, skin conductance, and blood glucose concentration.
- the sensed values obtained from these sensors may be used to automatically determine a current phase of a menstrual cycle of the user. Once the current phase of the menstrual cycle is known the basal dosages and/or the bolus dosages automatically may be adjusted to account for changes associated with the phase. The adjustments may be made over time as new phases of the menstrual cycle are reached.
- the exemplary embodiments may use a machine learning system to identify the phase of the menstrual cycle of the user from values obtained from the sensors.
- the machine learning system may learn the normal duration of each phase of the menstrual cycle as well as the normal length of a menstrual cycle for the user.
- the machine learning system may also learn how medicament sensitivity (such as insulin sensitivity) of the user varies over the course of the menstrual cycle for the user. In particular, the patterns of variance in magnitude and time may be learned.
- the machine learning system may rely upon a machine learning model that may utilize logistic regressors, random forests, deep learning networks, etc.
- the machine learning model may be trained on a data set derived from a large population of women and then may be customized to the user.
- the machine learning model may be trained solely on data derived from the user.
- the trained machine learning model may be used to identify the current phase of the menstrual cycle of the user.
- no machine learning system is used. Instead, conventional logic may be used to identify the current phase of the menstrual cycle of the user. In other exemplary embodiments, a user identifies when the user's menstrual cycle began, and may also identify how long her menstrual cycle typically lasts, and that information from the user is used by the control system to adjust the medicament dosages.
- FIG. 1A depicts an illustrative medicament delivery system 100 that is suitable for delivering a medicament to a user 108 in accordance with exemplary embodiments.
- the medicament delivery system 100 includes a medicament delivery device 102.
- the medicament delivery device 102 may be a wearable device that is worn on the body of the user 108 or carried by the user and having an infusion site.
- the medicament delivery device 102 may be directly coupled to a user (e.g., directly attached to a body part and/or skin of the user 108 via an adhesive or the like) or carried by the user (e.g., on a belt or in a pocket) with tubing connecting the medicament delivery device 102 to an infusion site where the medicament is injected.
- a surface of the medicament delivery device 102 may include an adhesive to facilitate attachment to the user 108.
- the medicament delivery device 102 may include a controller 110.
- the controller 110 may be implemented in hardware, software, or any combination thereof.
- the controller 110 may, for example, include a microprocessor, a logic circuit, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC) or a microcontroller coupled to a memory.
- the controller 110 may maintain a date and time as well as other functions (e.g., calculations or the like).
- the controller 110 may be operable to execute a control application 116 encoded in computer programming instructions stored in the storage 114 that enables the controller 110 to direct operation of the medicament delivery device 102.
- the controller may in some exemplary embodiments execute a model 115, such as machine learning model to perform functionality as detailed below.
- the model 115 is responsible for determining a current phase of the menstrual cycle of the user 108 and also learning patterns of key metrics, like heart rate, heart rate variability, skin temperature, and skin conductance over phases of the menstrual cycle of the user.
- the model 115 may also learn the average length of the phases of the menstrual cycle of the user and the average variation in insulin sensitivity over phases of the menstrual cycle of the user.
- the model 115 may be used to identify a current phase of the menstrual cycle of the user and to provide pattern information that is used to adapt basal dosages and bolus dosages of the medicament, like insulin.
- the model 115 may be realized in software.
- the control application 116 may control delivery of a medicament to the user 108 per a control approach like that described herein.
- the storage 114 may hold histories 111 for a user, such as a history of basal deliveries, a history of bolus deliveries, and/or other histories, such as a meal event history, exercise event history and/or the like.
- the controller 110 may be operable to receive data or information.
- the storage 114 may include both primary memory and secondary memory.
- the storage may include random access memory (RAM), read only memory (ROM), optical storage, magnetic storage, removable storage media, solid state storage or the like.
- the medicament delivery device 102 may include one or more housings for housing its various components including a pump 113, a power source, and a reservoir 112 for storing a medicament for delivery to the user 108 as warranted.
- a fluid path to the user 108 may be provided, and the medicament delivery device 102 may expel the medicament from the reservoir 112 to deliver the medicament to the user 108 using the pump 113 via the fluid path.
- the fluid path may, for example, include tubing coupling the medicament delivery device 102 to the user 108 (e.g., tubing coupling a cannula to the reservoir 112), and may include tubing to a separate infusion site.
- the medicament delivery device 102 may also include a user interface 117, such as an integrated display device for displaying information to the user 108 and in some embodiments, receiving information from the user 108.
- the user interface 117 may include a touchscreen and/or one or more input devices, such as buttons, knobs, or a keyboard.
- the medicament delivery device 102 may interface with a network 122.
- the network 122 may include a local area network (LAN), a wide area network (WAN) or a combination therein.
- a computing device 126 may be interfaced with the network, and the computing device may communicate with the medicament delivery device 102.
- the medicament delivery system 100 may include sensors 106 for sensing the levels of one or more analytes.
- the sensors 106 may be coupled to the user 108 by, for example, adhesive or the like and may provide information or data on one or more medical conditions and/or physical attributes of the user 108.
- the sensors 106 may be physically separate from the medicament delivery device 102 or may be an integrated component thereof.
- the medicament delivery system 100 may or may not also include a management device 104.
- a management device is not needed as medicament delivery device 102 may manage itself.
- the management device 104 may be a special purpose device, such as a dedicated personal diabetes manager (PDM) device.
- the management device 104 may be a programmed general-purpose device, such as any portable electronic device including, for example, a dedicated controller, such as processor, a micro-controller, or the like.
- the management device 104 may be used to program or adjust operation of the medicament delivery device 102 and/or the sensors 106.
- the management device 104 may be any portable electronic device including, for example, a dedicated device, a smartphone, a smartwatch or a tablet.
- the management device 104 may include a processor 119 and a storage 118.
- the processor 119 may execute processes to manage a user's blood glucose levels and to control the delivery of the medicament to the user 108.
- the model 115 may run on the processor 119 of the management device 104 in some embodiments.
- the medicament delivery device 102 may provide data from the sensors 106 and other data to the management device 104.
- the data may be stored in the storage 118.
- the processor 119 may also be operable to execute programming code stored in the storage 118.
- the storage may be operable to store one or more control applications 120 for execution by the processor 119.
- the one or more control applications 120 may be responsible for controlling the medicament delivery device 102, such as by controlling the AID delivery of insulin to the user 108.
- the storage 118 may store the one or more control applications 120, histories 121 like those described above for the_medicament delivery device 102, and other data and/or programs.
- the management device 104 may include a user interface (UI) 123 for communicating with the user 108.
- the user interface 123 may include a display, such as a touchscreen, for displaying information.
- the touchscreen may also be used to receive input when it is a touch screen.
- the user interface 123 may also include input elements, such as a keyboard, button, knobs, or the like.
- the management device 104 may interface with a network 124, such as a LAN or WAN or combination of such networks.
- the management device 104 may communicate over network 124 with one or more servers or cloud services 128.
- the model 115 and the data used by the model may be stored on the storage 131 for the cloud services/server(s) 128.
- the computational needs and the storage needs of the model 115 may be large, and the cloud services/server(s) 128 may be a suitable match for those needs.
- the data such as sensor values, may be sent for storage and processing from the medicament delivery device 102 directly to the cloud services/server(s) 128 or instead from the management device 104 to the cloud services/server(s) 128.
- the cloud services/server(s) 128 may provide output from the model 115 as needed to the management device 104 and/or medicament delivery device 102 during operation.
- Other devices like smartwatch 130, fitness monitor 132 and wearable device 134 may be part of the delivery system 100. These devices may communicate with the medicament delivery device 102 to receive information and/or issue commands to the medicament delivery device 102. These devices 130, 132 and 134 may execute computer programming instructions to perform some of the control functions otherwise performed by controller 110 or processor 119. These devices 130, 132 and 134 may include displays for displaying information. The display may show a user interface for providing input by the user, such as to request a change or pause in dosage or to request, initiate, or confirm delivery of a bolus of a medicament, or for displaying output, such as a change in dosage (e.g., of a basal delivery amount) as determined by controller 110 or management device 104. These devices 130, 132 and 134 may also have wireless communication connections with the sensor 106 to directly receive analyte measurement data.
- the medicament may be insulin for treating diabetes.
- the medicament may be glucagon for raising a user's blood glucose level.
- the medicament may also be a glucagon-like peptide (GLP)-1 receptor agonists for lowering blood glucose or slowing gastric emptying, thereby delaying spikes in blood glucose after a meal.
- GLP glucagon-like peptide
- FIG. 1B shows a block diagram 138 of examples of some sensors 106 that may be used in exemplary embodiments.
- the sensors 106 may gather information from the user 108 that help the model 115 to determine the current phase of the menstrual cycle of the user 108 and to help adapt to changing insulin sensitivity of the user over the phases of the menstrual cycle.
- the sensors 106 may include a skin temperature sensor 141 for sensing the skin temperature of the user at a suitable location, such as the wrist of the user or in proximity to the location of the medicament delivery device 102.
- the sensors 106 may include a heart rate monitor 142 for sensing the heart rate of the user 108.
- a skin conductance sensor 143 may be provided to measure the skin conductance of the user 108.
- An activity detector 144 such as an accelerometer, may be used to measure the activity level of the user.
- a glucose sensor 145 such as a continuous glucose monitor (CGM), may be provided.
- the glucose sensor 145 may be an on-body sensor that detects the blood glucose concentration of the user at regular intervals, such as every 5 minutes.
- Figure 1C depicts one exemplary configuration of the sensors 106 relative to the medicament delivery device 102.
- the medicament delivery device 102 includes a delivery device housing or housings 150 in which components of the medicament delivery device, like the controller 110, the reservoir 112, the pump 113 and the storage are contained.
- An accelerometer 160 may be contained inside the delivery device housing(s) 150.
- the accelerometer 160 acts as an activity detector 144 ( Figure 1B ) that may be used to determine if the user is sleeping, exercising, etc.
- the accelerometer 160 may also identify a magnitude of activity level of the user 108.
- the delivery device housing(s) 150 have an adhesive pad 152 attached to the bottom surface of the delivery device housing(s) 150.
- the adhesive pad 152 is secured to the delivery device housing(s) 150 by a suitable means such as by heat welding, an adhesive or other means.
- the adhesive pad 152 has an adhesive on its underside. The adhesive secures the adhesive pad 152 to the skin surface of the user 108.
- Certain sensors may be secured to the underside of the adhesive pad as shown. For example, a heart rate monitor 154, a skin temperature sensor 156, and a skin conductance sensor 158 may be secured to the underside of the adhesive pad and may contact the skin surface of the user 108.
- the exemplary embodiments may determine the current phase of the menstrual cycle of the user 108 and based on that determination may adjust the magnitude of the basal dosages and/or bolus dosages of medicament, such as insulin, to matching changing insulin sensitivity due to the phase of the menstrual cycle.
- Figure 2 depicts a breakdown of the phases of an idealized menstrual cycle 200. The depiction begins at the time that the user begins her period.
- the menstrual cycle 200 includes a follicular phase 202 that precedes ovulation and a luteal phase 202 that follows ovulation. Ovulation occurs during the peri-ovulation phase 210.
- the follicular phase 202 contains an early follicular phase 206 and a late follicular phase 208.
- the luteal phase 204 contains the early luteal phase 212, the mid luteal phase 214 and the late luteal phase 216.
- the days are numbered from 1 to 28 along the top of the phases in Figure 2 . The duration of these phases, and hence the total duration of the cycle, may vary among users.
- the insulin needs of users change over the phases of the menstrual cycle 200. Changes in estradiol and progesterone levels over the menstrual cycle 200 are correlated with changing insulin sensitivity. Insulin sensitivity is higher in the early follicular phase 206 as opposed to the luteal phase 204. The insulin needs of a user may vary by 25% within the menstrual cycle. The variations in insulin needs are not consistent for users. A customized approach is helpful. The exemplary embodiments provide such as customized approach.
- Figure 3 depicts a flowchart 300 of basic steps that may be performed in exemplary embodiments to compensate for changing insulin needs over the course of a menstrual cycle of a user 108.
- the current phase of the menstrual cycle of the user 108 is determined at 302. This may entail obtaining data from sensors connected to the user and processing the data to determine the current phase. Alternatively, this may entail simply prompting the user 108 to provide information from which the current phase may be derived. Once the current phase is known, the medicament delivery is adjusted based on the current phase at 304.
- the determination of the current phase of the menstrual cycle of the user 108 may be determined based on user provided information.
- the user 108 may be prompted to provide information regarding the start of the latest menstrual cycle. This may involve, for example, asking the user 108 to identify the date that their most recent period began.
- a prompt may be provided on the user interface 123 of the management device 104 or the user interface 117 of the medicament delivery device 102. The user might, for instance, be asked to choose a day on a monthly calendar (e.g., Figure 15 ).
- the information is obtained from the user. The obtained information identifies the date of the beginning of the menstrual cycle of the user and may be used to identify the current phase of the menstrual cycle based on the offset of the current date from the date that the menstrual cycle began.
- FIG. 4B depicts a flowchart 410 of illustrative steps that may be performed in exemplary embodiments when relying upon a model.
- the model 115 may be a deep learning model or other type of neural network model.
- the model 115 may use machine learning algorithms and may use logistic regressors, random forests, support vector machines boosting and bagging approaches and/or unsupervised learning methods.
- the model 115 automatically detects a current phase of the menstrual cycle of a user and learns trends in insulin sensitivity variation for the user.
- the machine learning model 115 is trained.
- the machine learning model 115 may be trained on data obtained from other women and then may be customized to the user 108. Alternatively, the machine learning model 115 may be trained solely on data for the user 108. For example, the medicament delivery device 102 may be secured to the user 108 and the sensors 106 may gather data for a period of two to three months. During this time, the machine learning model 115 may be in training mode. Once the training is complete, the machine learning model 115 is used to determine the current menstrual cycle phase of the user 108 at 414.
- Figure 5 depicts a block diagram 500 of the data flow for the machine learning model 504.
- the machine learning model 504 processes inputs 502 and generates an output 506 of the current menstrual cycle phase.
- Figure 6 depicts a diagram 600 showing some of the inputs that may be used by the machine learning model 602 in exemplary embodiments. Many of these inputs are sensor values 604.
- the sensor values may include values from sensors like those shown in Figure 1B of a skin temperature sensor 141, a heart rate sensor 142, a skin conductance sensor 143, an activity detector 144 and/or a glucose sensor 145.
- the sensor values 604 are segregated into nighttime readings (as indicated by time values when taken) and daytime readings where the user is at rest (as determined by the accelerometer readings or other activity level sensor readings). These values are more determinative of a current phase of menstrual cycle of the user 108 than values taken when the user 108 is active.
- the machine learning model 602 may use insulin delivery histories 606 as input. Carbohydrates consumed 608 may be input as well as user input values 610. Carbohydrate consumption levels may be indicative of a current phase of the menstrual cycle of the user 108.
- the machine learning model 602 may also receive time and/or date values 612 as input.
- Skin temperature generally drops in the follicular phase 202 and for most women is significantly higher in the luteal phase 204.
- Nightly heart rate may be lower than average in the follicular phase 202 and higher than average in the luteal phase 204.
- Nightly heart rate variability may be higher in the follicular phase 202 than average and lower than average in the luteal phase 204.
- Skin conductance may be lower in the follicular phase 202 than in other portions of the menstrual cycle. Increased carbohydrates are typically consumed during the luteal phase 204.
- the machine learning model 602 may determine whether the current phase of the user is the follicular phase 204 by performing the steps of the flowchart 700 in exemplary embodiments.
- the machine learning model 602 may be rules based in some exemplary embodiments.
- the flowchart 700 encodes some of the logic used by a general rule of the machine learning model 602. These steps may in some exemplary embodiments be performed by software that is not part of a machine learning model.
- Heart rate variability refers to the degree to which heart rate varies over a menstrual cycle and the mean heart rate variability refers to the average heart rate variability over multiple menstrual cycles, such as those for which data was gathered in the training. It is known that heart rate variability increases to be above average for many women during the follicular phase 204. If heart rate variability is not higher than the mean, it is concluded that the current phase is not a follicular phase at 708. If heart rate variability of the user is above the mean, the current heart rate of the user is compared to the mean heart rate at 706. If the current heart rate is above the mean heart rate, it is determined that the current phase is the follicular phase 204 at 710. Otherwise, the current phase is determined to not be the follicular phase at 708.
- Figure 8 depicts a flowchart 800 of logic that may be applied in exemplary embodiments by the machine learning model 602 or by logic to determine if the current phase is the luteal phase 204.
- a number of checks are made to see if sensed values are indicative of the current phase being the luteal phase 204.
- the flowchart 800 captures a general rule that may be applied by the machine learning model 602.
- a check is made whether a current skin temperature is higher than the mean skin temperature for the user 108. If not, the current phase is determined to not be the luteal phase at 808. If so, a check is made whether the current heart rate variability of the user is greater than the mean heart rate variability at 804.
- the current phase is determined to not be the luteal phase at 808. If so, at 806 a check is made if the heart rate of the user is less than the mean heart rate. If not, the current phase is determined to not be the luteal phase 204 at 808. If so, the current phase is determined to be the luteal phase 204 at 810.
- the machine learning model need not be limited to applying the general rules and logic of Figures 7 and 8 . Detailed individual rules may also be learned and applied by the machine learning model 602.
- the choice of current phase by the machine learning model 602 may be validated in multiple ways.
- One validation option is to look at previous decisions of a current phase made by the machine learning model 602.
- Figure 9A depicts a flowchart 900 of illustrative steps that may be performed by exemplary embodiments to perform such validation.
- the classification of phase for the previous day by the machine learning model 602 is compared with the classification of current phase chosen for the current day by the machine learning model 602.
- An analysis is made whether the classifications are consistent at 904. In other words, does the current day's classification of current phase make sense with yesterday's classification.
- FIG. 9B depicts a flowchart 920 of illustrative steps that may be performed in exemplary embodiments to validate the classification of the current phase.
- the nighttime blood glucose concentration levels for the user are obtained.
- the blood glucose sensor 145 may provide these values.
- These obtained sensor values are compared to the expected values for the current phase classification from the machine learning model 602 at 926. For example, if there is a reduction in nighttime blood glucose concentration levels relative to a baseline, it is an indication that there is increased insulin sensitivity.
- An increase in insulin sensitivity is associated with follicular phase 202 and a decrease in insulin sensitivity is associated with the luteal phase 204.
- a third approach to validation of a classification of the current phase by the machine learning model 602 is to validate relative to information provided by the user 108.
- Figure 9C depicts a flowchart 940 of illustrative steps that may be performed in exemplary embodiments to perform such validation.
- information is obtained from the user 108. For instance, the date that a last period of the user started may be obtained from the user. This may be compared at 944 to an expected value, e.g., the date the machine learning model 602 believes the menstrual cycle of the user began.
- a check is made whether the machine learning information (e.g., date) is consistent with the information (e.g., date) provided by the user 108. If inconsistent, the current phase classification by the machine learning model 602 is invalidated at 948. If consistent, the current phase classification by the machine learning model 602 is validated at 950.
- the three above-described validation approaches may be applied together, separately or in various combinations by the machine learning model 602 to validate preliminary classifications of the current phase of the menstrual cycle by the machine learning model. These validations may be performed before the classification of the current phase is used to adapt medicament dosages. The validations provide an added level of confidence that the classifications of current phase are accurate and reliable. The consequences of invalidation may be determined by the machine learning model 602. Invalidation may prompt the machine learning model 602 to repeat the classification of the current phase, for instance.
- FIG 10 depicts a diagram 1000 showing the inputs an output of the basal adaptivity mechanism 1006 of the exemplary embodiments.
- the basal adaptivity mechanism 1006 may be realized by computer programming instructions contained in the control applications 116 or 120.
- the basal adaptivity mechanism 1006 receives the classification of the current phase 1004 of the menstrual cycle of the user 108.
- the basal adaptivity mechanism 1006 also receives a most recent blood glucose concentration reading and information regarding excursions from past cycles (a cycle is, for example, a 5-minute interval).
- the basal adaptivity mechanism 1006 considers basal needs separately for nighttime, morning and daytime because the needs at these portions of the day tend to vary. As such, depending on the time of day, the basal adaptivity mechanism 1006 may produce a nighttime basal dosage 1008, a morning basal dosage 1010 or a daytime basal dosage 1012. In general, the basal adaptivity mechanism 1006 looks at the current menstrual phase classification 1004 and the historical blood glucose concentration trends in earlier menstrual cycles to adapt the basal dosage amounts 1008, 1010 and 1012. In general, the dosages of basal insulin are increased in the early luteal phase 212 and gradually return to normal levels at the end of the luteal phase 204. The adaptation is tailored to the individual user based on learned patterns. Past blood glucose concentration excursions 1002 are referenced in determining customized basal dosages.
- Figure 11A depicts a flowchart 1100 of illustrative steps that may be performed in exemplary embodiments for follicular phase 202 adjustments.
- decreases in insulin sensitivity are observed with some women in the follicular phase 202.
- the decreases in insulin sensitivity are determined. As mentioned above these decreases are determined by observation by the machine learning model 602.
- the basal insulin dosages are increased in the follicular phases to compensate for the decreased insulin sensitivity at 1104.
- Figure 11B depicts a flowchart 1110 of illustrative steps that may be performed in exemplary embodiments for luteal phase 204 adjustments.
- a determination of increases in insulin sensitivity in the luteal phase 204 is determined.
- the basal insulin dosages for the luteal phase 204 are decreased in response at 1114.
- Some examples help to illustrate the basal dosage adaptivity that may be provided.
- the adaptivity is customized to the particular user.
- Some women experience a reduction in insulin sensitivity of up to 25% in the early luteal phase 212. Typical reductions of insulin sensitivity are in excess of 5%.
- a nominal basal dosage would be set for the early follicular phase 206, the mid-late follicular phase 208 and the peri-ovulation phase 210.
- the basal dosage would be increased by 15% during the early luteal phase 212.
- the increase relative to the nominal basal dosage would be set at 10% in the mid luteal phase 214 and would be set at a 5% increase relative to the nominal basal dosage in the late luteal phase 216.
- Some women may experience an increased insulin sensitivity in the luteal phases 212, 214 and 216.
- the increases may be 5% in the early luteal phase, and 10% in the mid luteal phase 214.
- the basal dosage would be decreased by 5% relative to the nominal basal dosage in the early luteal phase 212 and would be decreased by 10% relative to the nominal basal dosage in the mid luteal phase 214.
- FIG. 12 depicts a diagram 120 showing illustrative inputs and outputs for a bolus adaptivity mechanism 1202.
- the bolus adaptivity mechanism 1202 may be realized as computer programming instructions in the control application 116. Inputs to the bolus adaptivity mechanism 1202 may include the classification of the current menstrual cycle phase 1206 and the current blood glucose concentration reading along with information regarding blood glucose concentration excursions from past cycles 1204. The bolus adaptivity mechanism 1202 processes these inputs 1204 and 1206 to produce an adapted insulin to carbohydrate ratio for the user and a bolus dosage amount 1208.
- Bolus dosages may be calculated when requested by the user 108.
- Figure 13 depicts a flowchart 1300 of illustrative steps that may be performed in exemplary embodiments to generate an adapted insulin bolus dosage based on the current phase of the menstrual cycle of the user 108.
- the user 108 requests a medicament bolus, such as a bolus of insulin.
- the current phase of the menstrual cycle of the user 108 is determined as discussed above.
- insulin sensitivity may vary with phase of the menstrual cycle.
- the exemplary embodiments may adapt for the changing insulin sensitivity by adapting the insulin to carbohydrates ratio (ICR), which may be used in determining the bolus dosage.
- the ICR is used to determine how much insulin is needed to compensate for a quantity of carbohydrates that is ingested.
- the ICR is decreased, whereas if insulin sensitivity decreases, the ICR is increased.
- the ICR for the current phase of the menstrual cycle of the user 108 is identified and at 1308 is used to calculate the bolus dosage.
- the magnitude of the increase in ICR or decrease in ICR is customized to the user's learned change in insulin sensitivity across the phases of the menstrual cycle of the user.
- the bolus dosage is proportional to the carbohydrates ingested and the ICR.
- the bolus dosage equals the grams of carbohydrates ingested divided by the ICR.
- ICR typically will be higher during the luteal phase 204 compared to the follicular phase 202.
- a suitable increase in the ICR for the luteal phase is 10% compared to the follicular phase 202.
- the ICR adaptation may follow the insulin sensitivity trend. As explained above, the insulin sensitivity changes at the individual level. As an example, suppose that the insulin sensitivity decreases in the early luteal phase 212 as described above, sensitivity changes the ICR would be reduced by 15% compared to baseline ICR in the early luteal phase 212, increased by 10% in the mid luteal phase 214 and reduced by 5% in the late luteal phase 216 compared to baseline ICR.
- the ICR may not be modulated through the menstrual period.
- the insulin sensitivity may be determined, such as described above, by looking at changes in blood glucose concentration for the user relative to the quantity of insulin delivered. If the area under the blood glucose curve is remaining the same, but the insulin delivery amount is increased, this means that the insulin sensitivity has been reduced (for the same blood sugar levels we are requiring more insulin). Conversely, if the area under the blood glucose curve remains the same, but the amount of insulin needed has reduced, then the insulin sensitivity has increased.
- comparing insulin sensitivity across the menstrual cycle one can compare the ratio of blood sugar area under the curve to insulin delivery and infer insulin sensitivity variation or the lack thereof. If the change in insulin sensitivity over the user's menstrual cycle is below a threshold based on the comparison, the modulation by menstrual cycle phase described herein may not be performed.
- the medicament delivery device 102 may include a user interface 117 and the management device 104 may include a user interface 123.
- the user interfaces 117 and 123 may be used to verify the phase that the machine learning model deems to be the current phase of the menstrual cycle.
- a display 1402 on a device 1400 (such as the medicament delivery device 102 or the management deice 104) may display a prompt 1406 for the user to verify and/or input the date that her last period began on.
- Buttons 1408 may be selected to verify (selecting "Y") or not verify (selecting "N") the displayed date. Buttons may be used to adjust the date rather than selecting a "Y" or "N" to verify the date.
- the display 1402 may also be used to verify a change in the basal dosage. As shown in Figure 14B , a message 1410 that may be displayed on display 1402 to prompt the user to accept or reject the proposed increase in basal dosage. A user interface screen or informational text may also be displayed to inform the user as to why an increase or decrease of X% (e.g., 10%) of the basal dosage is being recommended by the system. Buttons 1412 enable the user 108 to accept or reject the proposed increase. The display 1402 may also display a request 1414 to accept or reject a proposed reduction in ICR by choosing buttons 1416 as shown in Figure 14C .
- X% e.g. 10%
- a user interface screen or informational text may also be displayed to inform the user as to why an increase or decrease of the ICR (e.g., -15%) is being recommended by the system.
- a request 1418 to reduce or increase the ICR may be displayed on the display 1402.
- Buttons 1420 enable the user to accept or reject the reduction.
- Such buttons, confirmations, recommendations, and/or informational text may be displayed and/or used throughout the menstrual cycle.
- Figure 15 shows an illustrative user interface 1500 for soliciting information from the user 108.
- the user interface includes a section 1502 for obtaining information regarding the start date of the user's last period.
- the section 1502 includes a calendar 1504 that shows a month.
- Text 1506 identifies the month and year that is displayed.
- the current date is identified by a highlight box 1508.
- An up arrow and a down arrow 1510 may be selected to choose the next month or the previous month, respectively.
- the user 108 simply clicks on the day of the month on which her last period started. This information is then recorded and stored, such as in storage 114.
- the user interface 1500 may also include a text box 1512 for the user 108 to specify the number of days her period typically lasts.
- the user 108 may enter a value 1514 in the text box 1512 or may be select the + button 1516 to increase the displayed value 1514 or the - button to decrease the displayed value by increments of 1.
- a text box 1520 may be provided for the user 108 to specify the average number of days in her menstrual cycle.
- the user 108 may enter a value 1522 in the text box 1520 or use the + button 1524 and/or - button to select the correct value.
- the information gathered from the user may be stored in storage 114. This information may be used by the model 155 and the controller 110 as described above.
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- Chemical & Material Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medicinal Chemistry (AREA)
- General Business, Economics & Management (AREA)
- Veterinary Medicine (AREA)
- Heart & Thoracic Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Pathology (AREA)
- Diabetes (AREA)
- Hematology (AREA)
- Anesthesiology (AREA)
- Vascular Medicine (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
Exemplary embodiments account for differing needs of a user over the menstrual cycle of the user to better control the blood glucose concentration of the user. The exemplary embodiments may be realized in control systems for medicament delivery devices that deliver medicaments, such as medicaments that regulate blood glucose concentration levels. Examples of such medicaments that regulate blood glucose concentration levels include insulin, glucagon, and glucagon peptide-1 (GLP-1) agonists. The exemplary embodiments are able to better tailor the dosages of the medicament delivered to the user with the medicament delivery device to reduce the risk of hyperglycemia and hypoglycemia and help reduce blood glucose concentration excursions.
Description
- A conventional medicament delivery device may deliver medicament at basal dosages and/or bolus dosages. The basal dosages are delivered on an-ongoing basis and aim to address a substantial portion of the need for the medicament on an on-going basis. The bolus dosages are delivered when requested by a user or when the control system for the medicament delivery device concludes based on information regarding the user that there is a need to deliver the bolus dosage. In some instances, the basal dosages are delivered automatically by the medicament delivery device to the user. The control system is generally responsible for determining the timing and the dosages for such medicament deliveries.
- One example of a conventional medicament delivery device is an insulin delivery device, such as an insulin pump or patch. The conventional insulin delivery device may calculate a basal dosage based on total daily insulin (TDI). TDI represents the aggregate amount of insulin needed by the user for a day. TDI is typically calculated based on the weight of the user. A commonly used formula is that TDI equals user weight in pounds divided by 4. Thus, the TDI for a 200-pound man is 200 divided by 4 or 50 units of insulin. The basal dosage is conventionally determined to be one half of TDI.
- Insulin boluses are typically delivered in response to meals by the user. The meals will increase the user's blood glucose concentration. The magnitude of the increase in blood glucose concentration is related to the quantity of carbohydrates ingested. Thus, a conventional insulin delivery device may determine what dosage of insulin will compensate for the quantity of carbohydrates ingested. In order to determine the amount of insulin needed and hence the bolus dosage, the conventional insulin delivery system may multiply the carbohydrates ingested by the insulin to carbohydrates ratio (ICR). The ICR conventionally may be set as a value typically selected from the range of 4 to 50. For example, a value of 4 for the ICR implies that 1 unit of insulin is to be delivered for every 4 grams of carbohydrates ingested. The conventional insulin delivery system may also look at the current blood glucose concentration and the insulin on board (IOB) for the user, which represents the quantity of insulin delivered to user that still has insulin action remaining.
- In accordance with an inventive aspect of an embodiment, a method is performed by a processor in an electronic device. The method includes receiving information regarding a menstrual cycle of a user and based on the received information regarding a menstrual cycle of a user, adjusting a medicament dosage to be delivered by an automated medicament delivery device.
- The received information may be a current phase of a menstrual cycle of the user. The received information may be received from a machine learning model. The received information may be information from which a current phase of the menstrual cycle is determined. The received information may include information from one or more sensors secured to the user. The medicament may be one of insulin, glucagon or a glucagon peptide-1 (GLP-1) agonist. The adjusting may include adjusting an insulin dosage to be delivered by the automated medicament delivery device based on an insulin sensitivity of the user for a current phase of the menstrual cycle of the user.
- In accordance with another inventive feature of an embodiment, a method is performed by a processor in an electronic device. The method includes receiving input from a sensor. Based at least in part on the received input, a phase of a menstrual cycle of a user is determined with the processor. The method also includes determining insulin sensitivity of the user with the processor based on the determined phase of the menstrual cycle and adjusting the insulin delivered by a delivery device based on the determined insulin sensitivity.
- The sensor may sense skin temperature, heart rate, skin conductance, or activity level. The method may further include receiving additional inputs from multiple sensors and using the additional inputs in the determining of the phase of the menstrual cycle of the user. The additional inputs from the multiple sensors may include a blood glucose concentration value for the user from one of the sensors that is a glucose monitor. The adjusting may adjust a size of a dosage of basal insulin to be delivered by the delivery device. The adjusting may adjust a size of dosage of an insulin bolus to be delivered by the delivery device.
- In accordance with an additional aspect of an embodiment, a method is performed by a processor in an electronic device. Per the method, patterns of medicament sensitivity of a user based on a phase of a menstrual cycle of a user are learned by a machine learning model executing on the processor. Delivery of medicament to the user are adjusted by the processor based on the learned patterns to be delivered by a medicament delivery device to the user.
- The method may further include receiving input from at least one sensor that senses information regarding the user and processing the input to determine a current phase of the menstrual cycle of the user. The input may include heart rate and skin temperature. The input may include blood glucose concentration and an indication of activity level. The learning may include training on a data set derived from women other than the user and subsequent to the training on the data set, training on data from the user to customize the machine learning model to the user. The medicament may be one of insulin, glucagon or a glucagon peptide-1 (GLP-1) agonist, for example.
-
-
Figure 1A depicts an illustrative medicament delivery system that is suitable for delivering a medicament to a user in accordance with exemplary embodiments. -
Figure 1B shows a block diagram of examples of some sensors that may be used in exemplary embodiments. -
Figure 1C depicts one exemplary configuration of the sensors relative to the medicament delivery device. -
Figure 2 depicts a breakdown of the phases of an idealized menstrual cycle. -
Figure 3 depicts a flowchart of basic steps that may be performed in exemplary embodiments to compensate for changing insulin needs over the course of a menstrual cycle of a user. -
Figure 4A depicts a flowchart of illustrative steps that may be performed in exemplary embodiments to determine a current phase of a menstrual cycle of a user based on user-provided information. -
Figure 4B depicts a flowchart of illustrative steps that may be performed in exemplary embodiments to determine a current phase of a menstrual cycle of a user using a model. -
Figure 5 depicts a block diagram of the data flow for the machine learning model in exemplary embodiments. -
Figure 6 depicts a diagram showing some of the inputs that may be used by the machine learning model in exemplary embodiments. -
Figure 7 depicts a flowchart of illustrative steps that may be performed to determine in the current phase of the menstrual cycle of the user is the follicular phase. -
Figure 8 depicts a flowchart of illustrative steps that may be performed to determine in the current phase of the menstrual cycle of the user is the luteal phase. -
Figure 9A depicts a flowchart of illustrative steps that may be performed by exemplary embodiments to perform validation of the current phase of the menstrual cycle of the user based on the phase determined for the previous day. -
Figure 9B depicts a flowchart of illustrative steps that may be performed by exemplary embodiments to perform validation of current phase of the menstrual cycle of the user based on blood glucose concentration values. -
Figure 9C depicts a flowchart of illustrative steps that may be performed by exemplary embodiments to perform validation of current phase of the menstrual cycle of the user based on user-provided information. -
Figure 10 depicts a diagram showing the inputs and output of the basal adaptivity mechanism of the exemplary embodiments. -
Figure 11A depicts a flowchart of illustrative steps that may be performed in exemplary embodiments for follicular phase adjustments. -
Figure 11B depicts a flowchart of illustrative steps that may be performed in exemplary embodiments for luteal phase adjustments. -
Figure 12 depicts a diagram showing illustrative inputs and outputs for a bolus adaptivity mechanism. -
Figure 13 depicts a flowchart of illustrative steps that may be performed in exemplary embodiments to generate an adapted insulin bolus dosage based on current phase of the menstrual cycle of the user. -
Figures 14A-14D depict illustrative user interfaces. -
Figure 15 depicts an illustrative user interface for soliciting information from a user regarding the user's menstrual cycle. - The true medicament dosage needs of a user may vary from user to user. Moreover, the true medicament needs of a given user may vary over ranges of days or weeks and may vary even during a single day. Unfortunately, conventional medicament delivery devices do not account for many of these variations in medicament dosage needs. For example, a user's medicament dosage needs may vary based on the menstrual cycle of the user. One instance of this variation is that insulin sensitivity of a user may vary over the course of the menstrual cycle. Conventional insulin delivery devices do not account for this variation in insulin sensitivity due to the menstrual cycle phase of the user. This can be problematic in that the insulin needs of the user change over the course of the menstrual cycle of the user, but the conventional insulin delivery devices do not adjust for the change. As a result, the user may be at greater risk of hyperglycemia or hypoglycemia.
- Exemplary embodiments described herein account for the differing needs of the user over the menstrual cycle of the user to better control the blood glucose concentration of the user. The exemplary embodiments may be realized in control systems for medicament delivery devices that deliver medicaments, such as medicaments that regulate blood glucose concentration levels. Examples of such medicaments that regulate blood glucose concentration levels include insulin, glucagon, and glucagon peptide-1 (GLP-1) agonists. The exemplary embodiments are able to better tailor the dosages of the medicament delivered to the user with the medicament delivery device to reduce the risk of hyperglycemia and hypoglycemia and help reduce blood glucose concentration excursions.
- Some exemplary embodiments may use sensors, such as sensors of heart rate, skin temperature, skin conductance, and blood glucose concentration. The sensed values obtained from these sensors may be used to automatically determine a current phase of a menstrual cycle of the user. Once the current phase of the menstrual cycle is known the basal dosages and/or the bolus dosages automatically may be adjusted to account for changes associated with the phase. The adjustments may be made over time as new phases of the menstrual cycle are reached.
- The exemplary embodiments may use a machine learning system to identify the phase of the menstrual cycle of the user from values obtained from the sensors. The machine learning system may learn the normal duration of each phase of the menstrual cycle as well as the normal length of a menstrual cycle for the user. The machine learning system may also learn how medicament sensitivity (such as insulin sensitivity) of the user varies over the course of the menstrual cycle for the user. In particular, the patterns of variance in magnitude and time may be learned.
- In some exemplary embodiments, the machine learning system may rely upon a machine learning model that may utilize logistic regressors, random forests, deep learning networks, etc. The machine learning model may be trained on a data set derived from a large population of women and then may be customized to the user. Alternatively, the machine learning model may be trained solely on data derived from the user. The trained machine learning model may be used to identify the current phase of the menstrual cycle of the user.
- In some exemplary embodiments no machine learning system is used. Instead, conventional logic may be used to identify the current phase of the menstrual cycle of the user. In other exemplary embodiments, a user identifies when the user's menstrual cycle began, and may also identify how long her menstrual cycle typically lasts, and that information from the user is used by the control system to adjust the medicament dosages.
-
Figure 1A depicts an illustrativemedicament delivery system 100 that is suitable for delivering a medicament to auser 108 in accordance with exemplary embodiments. Themedicament delivery system 100 includes amedicament delivery device 102. Themedicament delivery device 102 may be a wearable device that is worn on the body of theuser 108 or carried by the user and having an infusion site. Themedicament delivery device 102 may be directly coupled to a user (e.g., directly attached to a body part and/or skin of theuser 108 via an adhesive or the like) or carried by the user (e.g., on a belt or in a pocket) with tubing connecting themedicament delivery device 102 to an infusion site where the medicament is injected. In a preferred embodiment, a surface of themedicament delivery device 102 may include an adhesive to facilitate attachment to theuser 108. - The
medicament delivery device 102 may include acontroller 110. Thecontroller 110 may be implemented in hardware, software, or any combination thereof. Thecontroller 110 may, for example, include a microprocessor, a logic circuit, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC) or a microcontroller coupled to a memory. Thecontroller 110 may maintain a date and time as well as other functions (e.g., calculations or the like). Thecontroller 110 may be operable to execute acontrol application 116 encoded in computer programming instructions stored in thestorage 114 that enables thecontroller 110 to direct operation of themedicament delivery device 102. The controller may in some exemplary embodiments execute amodel 115, such as machine learning model to perform functionality as detailed below. In some embodiments, themodel 115 is responsible for determining a current phase of the menstrual cycle of theuser 108 and also learning patterns of key metrics, like heart rate, heart rate variability, skin temperature, and skin conductance over phases of the menstrual cycle of the user. Themodel 115 may also learn the average length of the phases of the menstrual cycle of the user and the average variation in insulin sensitivity over phases of the menstrual cycle of the user. Themodel 115 may be used to identify a current phase of the menstrual cycle of the user and to provide pattern information that is used to adapt basal dosages and bolus dosages of the medicament, like insulin. Themodel 115 may be realized in software. - The
control application 116 may control delivery of a medicament to theuser 108 per a control approach like that described herein. Thestorage 114 may holdhistories 111 for a user, such as a history of basal deliveries, a history of bolus deliveries, and/or other histories, such as a meal event history, exercise event history and/or the like. In addition, thecontroller 110 may be operable to receive data or information. Thestorage 114 may include both primary memory and secondary memory. The storage may include random access memory (RAM), read only memory (ROM), optical storage, magnetic storage, removable storage media, solid state storage or the like. - The
medicament delivery device 102 may include one or more housings for housing its various components including apump 113, a power source, and areservoir 112 for storing a medicament for delivery to theuser 108 as warranted. A fluid path to theuser 108 may be provided, and themedicament delivery device 102 may expel the medicament from thereservoir 112 to deliver the medicament to theuser 108 using thepump 113 via the fluid path. The fluid path may, for example, include tubing coupling themedicament delivery device 102 to the user 108 (e.g., tubing coupling a cannula to the reservoir 112), and may include tubing to a separate infusion site. - There may be one or more communications links with one or more devices physically separated from the
medicament delivery device 102 including, for example, amanagement device 104 of the user and/or a caregiver of the user and/or asensor 106. The communication links may include any wired or wireless communication links operating according to any known communications protocol or standard, such as Bluetooth®, Wi-Fi, a near-field communication standard, a cellular standard, or any other wireless protocol. Themedicament delivery device 102 may also include auser interface 117, such as an integrated display device for displaying information to theuser 108 and in some embodiments, receiving information from theuser 108. Theuser interface 117 may include a touchscreen and/or one or more input devices, such as buttons, knobs, or a keyboard. - The
medicament delivery device 102 may interface with anetwork 122. Thenetwork 122 may include a local area network (LAN), a wide area network (WAN) or a combination therein. Acomputing device 126 may be interfaced with the network, and the computing device may communicate with themedicament delivery device 102. - The
medicament delivery system 100 may includesensors 106 for sensing the levels of one or more analytes. Thesensors 106 may be coupled to theuser 108 by, for example, adhesive or the like and may provide information or data on one or more medical conditions and/or physical attributes of theuser 108. Thesensors 106 may be physically separate from themedicament delivery device 102 or may be an integrated component thereof. - The
medicament delivery system 100 may or may not also include amanagement device 104. In some embodiments, a management device is not needed asmedicament delivery device 102 may manage itself. Themanagement device 104 may be a special purpose device, such as a dedicated personal diabetes manager (PDM) device. Themanagement device 104 may be a programmed general-purpose device, such as any portable electronic device including, for example, a dedicated controller, such as processor, a micro-controller, or the like. Themanagement device 104 may be used to program or adjust operation of themedicament delivery device 102 and/or thesensors 106. Themanagement device 104 may be any portable electronic device including, for example, a dedicated device, a smartphone, a smartwatch or a tablet. In the depicted example, themanagement device 104 may include aprocessor 119 and astorage 118. Theprocessor 119 may execute processes to manage a user's blood glucose levels and to control the delivery of the medicament to theuser 108. Themodel 115 may run on theprocessor 119 of themanagement device 104 in some embodiments. Themedicament delivery device 102 may provide data from thesensors 106 and other data to themanagement device 104. The data may be stored in thestorage 118. Theprocessor 119 may also be operable to execute programming code stored in thestorage 118. For example, the storage may be operable to store one ormore control applications 120 for execution by theprocessor 119. The one ormore control applications 120 may be responsible for controlling themedicament delivery device 102, such as by controlling the AID delivery of insulin to theuser 108. Thestorage 118 may store the one ormore control applications 120,histories 121 like those described above forthe_medicament delivery device 102, and other data and/or programs. - The
management device 104 may include a user interface (UI) 123 for communicating with theuser 108. Theuser interface 123 may include a display, such as a touchscreen, for displaying information. The touchscreen may also be used to receive input when it is a touch screen. Theuser interface 123 may also include input elements, such as a keyboard, button, knobs, or the like. - The
management device 104 may interface with anetwork 124, such as a LAN or WAN or combination of such networks. Themanagement device 104 may communicate overnetwork 124 with one or more servers orcloud services 128. In some exemplary embodiment, themodel 115 and the data used by the model may be stored on thestorage 131 for the cloud services/server(s) 128. The computational needs and the storage needs of themodel 115 may be large, and the cloud services/server(s) 128 may be a suitable match for those needs. In such instances, the data, such as sensor values, may be sent for storage and processing from themedicament delivery device 102 directly to the cloud services/server(s) 128 or instead from themanagement device 104 to the cloud services/server(s) 128. The cloud services/server(s) 128 may provide output from themodel 115 as needed to themanagement device 104 and/ormedicament delivery device 102 during operation. - Other devices, like
smartwatch 130,fitness monitor 132 andwearable device 134 may be part of thedelivery system 100. These devices may communicate with themedicament delivery device 102 to receive information and/or issue commands to themedicament delivery device 102. Thesedevices controller 110 orprocessor 119. Thesedevices controller 110 ormanagement device 104. Thesedevices sensor 106 to directly receive analyte measurement data. - A wide variety of medicaments may be delivered by the
medicament delivery device 102. The medicament may be insulin for treating diabetes. The medicament may be glucagon for raising a user's blood glucose level. The medicament may also be a glucagon-like peptide (GLP)-1 receptor agonists for lowering blood glucose or slowing gastric emptying, thereby delaying spikes in blood glucose after a meal. -
Figure 1B shows a block diagram 138 of examples of somesensors 106 that may be used in exemplary embodiments. Thesensors 106 may gather information from theuser 108 that help themodel 115 to determine the current phase of the menstrual cycle of theuser 108 and to help adapt to changing insulin sensitivity of the user over the phases of the menstrual cycle. Thesensors 106 may include askin temperature sensor 141 for sensing the skin temperature of the user at a suitable location, such as the wrist of the user or in proximity to the location of themedicament delivery device 102. Thesensors 106 may include aheart rate monitor 142 for sensing the heart rate of theuser 108. Askin conductance sensor 143 may be provided to measure the skin conductance of theuser 108. Anactivity detector 144, such as an accelerometer, may be used to measure the activity level of the user. Aglucose sensor 145, such as a continuous glucose monitor (CGM), may be provided. Theglucose sensor 145 may be an on-body sensor that detects the blood glucose concentration of the user at regular intervals, such as every 5 minutes. -
Figure 1C depicts one exemplary configuration of thesensors 106 relative to themedicament delivery device 102. As shown inFigure 1C , in some exemplary embodiments, themedicament delivery device 102 includes a delivery device housing orhousings 150 in which components of the medicament delivery device, like thecontroller 110, thereservoir 112, thepump 113 and the storage are contained. Anaccelerometer 160 may be contained inside the delivery device housing(s) 150. Theaccelerometer 160 acts as an activity detector 144 (Figure 1B ) that may be used to determine if the user is sleeping, exercising, etc. Theaccelerometer 160 may also identify a magnitude of activity level of theuser 108. - The delivery device housing(s) 150 have an
adhesive pad 152 attached to the bottom surface of the delivery device housing(s) 150. Theadhesive pad 152 is secured to the delivery device housing(s) 150 by a suitable means such as by heat welding, an adhesive or other means. Theadhesive pad 152 has an adhesive on its underside. The adhesive secures theadhesive pad 152 to the skin surface of theuser 108. Certain sensors may be secured to the underside of the adhesive pad as shown. For example, aheart rate monitor 154, askin temperature sensor 156, and askin conductance sensor 158 may be secured to the underside of the adhesive pad and may contact the skin surface of theuser 108. - The exemplary embodiments may determine the current phase of the menstrual cycle of the
user 108 and based on that determination may adjust the magnitude of the basal dosages and/or bolus dosages of medicament, such as insulin, to matching changing insulin sensitivity due to the phase of the menstrual cycle.Figure 2 depicts a breakdown of the phases of an idealizedmenstrual cycle 200. The depiction begins at the time that the user begins her period. Themenstrual cycle 200 includes afollicular phase 202 that precedes ovulation and aluteal phase 202 that follows ovulation. Ovulation occurs during theperi-ovulation phase 210. Thefollicular phase 202 contains an earlyfollicular phase 206 and a latefollicular phase 208. Theluteal phase 204 contains the earlyluteal phase 212, the midluteal phase 214 and the lateluteal phase 216. The days are numbered from 1 to 28 along the top of the phases inFigure 2 . The duration of these phases, and hence the total duration of the cycle, may vary among users. - The insulin needs of users change over the phases of the
menstrual cycle 200. Changes in estradiol and progesterone levels over themenstrual cycle 200 are correlated with changing insulin sensitivity. Insulin sensitivity is higher in the earlyfollicular phase 206 as opposed to theluteal phase 204. The insulin needs of a user may vary by 25% within the menstrual cycle. The variations in insulin needs are not consistent for users. A customized approach is helpful. The exemplary embodiments provide such as customized approach. -
Figure 3 depicts aflowchart 300 of basic steps that may be performed in exemplary embodiments to compensate for changing insulin needs over the course of a menstrual cycle of auser 108. First, the current phase of the menstrual cycle of theuser 108 is determined at 302. This may entail obtaining data from sensors connected to the user and processing the data to determine the current phase. Alternatively, this may entail simply prompting theuser 108 to provide information from which the current phase may be derived. Once the current phase is known, the medicament delivery is adjusted based on the current phase at 304. - As shown in the
flowchart 400 ofFigure 4A , the determination of the current phase of the menstrual cycle of theuser 108 may be determined based on user provided information. At 402, theuser 108 may be prompted to provide information regarding the start of the latest menstrual cycle. This may involve, for example, asking theuser 108 to identify the date that their most recent period began. A prompt may be provided on theuser interface 123 of themanagement device 104 or theuser interface 117 of themedicament delivery device 102. The user might, for instance, be asked to choose a day on a monthly calendar (e.g.,Figure 15 ). At 404, the information is obtained from the user. The obtained information identifies the date of the beginning of the menstrual cycle of the user and may be used to identify the current phase of the menstrual cycle based on the offset of the current date from the date that the menstrual cycle began. - Another option to determining the current phase of the menstrual cycle of the
user 108 is to rely upon amodel 115.Figure 4B depicts aflowchart 410 of illustrative steps that may be performed in exemplary embodiments when relying upon a model. Themodel 115 may be a deep learning model or other type of neural network model. Themodel 115 may use machine learning algorithms and may use logistic regressors, random forests, support vector machines boosting and bagging approaches and/or unsupervised learning methods. Themodel 115 automatically detects a current phase of the menstrual cycle of a user and learns trends in insulin sensitivity variation for the user. At 412, themachine learning model 115 is trained. Themachine learning model 115 may be trained on data obtained from other women and then may be customized to theuser 108. Alternatively, themachine learning model 115 may be trained solely on data for theuser 108. For example, themedicament delivery device 102 may be secured to theuser 108 and thesensors 106 may gather data for a period of two to three months. During this time, themachine learning model 115 may be in training mode. Once the training is complete, themachine learning model 115 is used to determine the current menstrual cycle phase of theuser 108 at 414. -
Figure 5 depicts a block diagram 500 of the data flow for themachine learning model 504. Themachine learning model 504processes inputs 502 and generates anoutput 506 of the current menstrual cycle phase.Figure 6 depicts a diagram 600 showing some of the inputs that may be used by themachine learning model 602 in exemplary embodiments. Many of these inputs aresensor values 604. For example, the sensor values may include values from sensors like those shown inFigure 1B of askin temperature sensor 141, aheart rate sensor 142, askin conductance sensor 143, anactivity detector 144 and/or aglucose sensor 145. The sensor values 604 are segregated into nighttime readings (as indicated by time values when taken) and daytime readings where the user is at rest (as determined by the accelerometer readings or other activity level sensor readings). These values are more determinative of a current phase of menstrual cycle of theuser 108 than values taken when theuser 108 is active. Themachine learning model 602 may useinsulin delivery histories 606 as input. Carbohydrates consumed 608 may be input as well as user input values 610. Carbohydrate consumption levels may be indicative of a current phase of the menstrual cycle of theuser 108. Themachine learning model 602 may also receive time and/ordate values 612 as input. - Skin temperature generally drops in the
follicular phase 202 and for most women is significantly higher in theluteal phase 204. Nightly heart rate may be lower than average in thefollicular phase 202 and higher than average in theluteal phase 204. Nightly heart rate variability may be higher in thefollicular phase 202 than average and lower than average in theluteal phase 204. Skin conductance may be lower in thefollicular phase 202 than in other portions of the menstrual cycle. Increased carbohydrates are typically consumed during theluteal phase 204. These observations may be used by the logic or themachine learning model 602 to determine current phase of the menstrual cycle of the user. - The
machine learning model 602 may determine whether the current phase of the user is thefollicular phase 204 by performing the steps of theflowchart 700 in exemplary embodiments. Themachine learning model 602 may be rules based in some exemplary embodiments. Theflowchart 700 encodes some of the logic used by a general rule of themachine learning model 602. These steps may in some exemplary embodiments be performed by software that is not part of a machine learning model. - At 702, a determination is made whether a current skin temperature of the
user 108 is greater than a mean skin temperature of the user over a time interval, such as over one or more menstrual cycles. This check is made because, in general, during the follicular phase the skin temperature of a woman is elevated above the mean skin temperature. If not, the conclusion is reached that the current phase is not a follicular phase at 708. If the skin temperature is greater than the average skin temperature, the variability of the heart rate of theuser 108 is compared to the mean heart rate variability of the user to determine if the heart rate variability is greater than the average heart rate variability over an interval at 704. Heart rate variability refers to the degree to which heart rate varies over a menstrual cycle and the mean heart rate variability refers to the average heart rate variability over multiple menstrual cycles, such as those for which data was gathered in the training. It is known that heart rate variability increases to be above average for many women during thefollicular phase 204. If heart rate variability is not higher than the mean, it is concluded that the current phase is not a follicular phase at 708. If heart rate variability of the user is above the mean, the current heart rate of the user is compared to the mean heart rate at 706. If the current heart rate is above the mean heart rate, it is determined that the current phase is thefollicular phase 204 at 710. Otherwise, the current phase is determined to not be the follicular phase at 708. -
Figure 8 depicts a flowchart 800 of logic that may be applied in exemplary embodiments by themachine learning model 602 or by logic to determine if the current phase is theluteal phase 204. In general, a number of checks are made to see if sensed values are indicative of the current phase being theluteal phase 204. The flowchart 800 captures a general rule that may be applied by themachine learning model 602. At 802, a check is made whether a current skin temperature is higher than the mean skin temperature for theuser 108. If not, the current phase is determined to not be the luteal phase at 808. If so, a check is made whether the current heart rate variability of the user is greater than the mean heart rate variability at 804. If not, the current phase is determined to not be the luteal phase at 808. If so, at 806 a check is made if the heart rate of the user is less than the mean heart rate. If not, the current phase is determined to not be theluteal phase 204 at 808. If so, the current phase is determined to be theluteal phase 204 at 810. - The machine learning model need not be limited to applying the general rules and logic of
Figures 7 and8 . Detailed individual rules may also be learned and applied by themachine learning model 602. - The choice of current phase by the
machine learning model 602 may be validated in multiple ways. One validation option is to look at previous decisions of a current phase made by themachine learning model 602.Figure 9A depicts aflowchart 900 of illustrative steps that may be performed by exemplary embodiments to perform such validation. At 902, the classification of phase for the previous day by themachine learning model 602 is compared with the classification of current phase chosen for the current day by themachine learning model 602. An analysis is made whether the classifications are consistent at 904. In other words, does the current day's classification of current phase make sense with yesterday's classification. For example, if yesterday's classification was the early follicular phase and today's classification was the mid luteal phase, there is an inconsistency as these phases are not adjacent to each other and do not follow each other. If there is an inconsistency, the classification of the current phase is invalidated at 906. If there is not an inconsistency, the classification of the current phase is validated at 908. - Another validation option is to look at the blood glucose concentration levels for the user to validate the classification of the current phase by the
machine learning model 602.Figure 9B depicts aflowchart 920 of illustrative steps that may be performed in exemplary embodiments to validate the classification of the current phase. At 922, the nighttime blood glucose concentration levels for the user are obtained. Theblood glucose sensor 145 may provide these values. These obtained sensor values are compared to the expected values for the current phase classification from themachine learning model 602 at 926. For example, if there is a reduction in nighttime blood glucose concentration levels relative to a baseline, it is an indication that there is increased insulin sensitivity. An increase in insulin sensitivity is associated withfollicular phase 202 and a decrease in insulin sensitivity is associated with theluteal phase 204. At 926, a check is made whether the nighttime blood glucose concentration levels are consistent with the classification of the current phase by themachine learning model 602. If not, the classification of the current phase is invalidated at 928. If so, the classification of the current phase is validated at 930. - A third approach to validation of a classification of the current phase by the
machine learning model 602 is to validate relative to information provided by theuser 108.Figure 9C depicts aflowchart 940 of illustrative steps that may be performed in exemplary embodiments to perform such validation. At 942, information is obtained from theuser 108. For instance, the date that a last period of the user started may be obtained from the user. This may be compared at 944 to an expected value, e.g., the date themachine learning model 602 believes the menstrual cycle of the user began. At 946, a check is made whether the machine learning information (e.g., date) is consistent with the information (e.g., date) provided by theuser 108. If inconsistent, the current phase classification by themachine learning model 602 is invalidated at 948. If consistent, the current phase classification by themachine learning model 602 is validated at 950. - The three above-described validation approaches may be applied together, separately or in various combinations by the
machine learning model 602 to validate preliminary classifications of the current phase of the menstrual cycle by the machine learning model. These validations may be performed before the classification of the current phase is used to adapt medicament dosages. The validations provide an added level of confidence that the classifications of current phase are accurate and reliable. The consequences of invalidation may be determined by themachine learning model 602. Invalidation may prompt themachine learning model 602 to repeat the classification of the current phase, for instance. - Once the current phase of the menstrual cycle of the
user 108 is determined, the basal dosage of medicament to be delivered by themedicament delivery device 102 may be adjusted as needed.Figure 10 depicts a diagram 1000 showing the inputs an output of thebasal adaptivity mechanism 1006 of the exemplary embodiments. Thebasal adaptivity mechanism 1006 may be realized by computer programming instructions contained in thecontrol applications basal adaptivity mechanism 1006 receives the classification of thecurrent phase 1004 of the menstrual cycle of theuser 108. Thebasal adaptivity mechanism 1006 also receives a most recent blood glucose concentration reading and information regarding excursions from past cycles (a cycle is, for example, a 5-minute interval). Thebasal adaptivity mechanism 1006 considers basal needs separately for nighttime, morning and daytime because the needs at these portions of the day tend to vary. As such, depending on the time of day, thebasal adaptivity mechanism 1006 may produce a nighttimebasal dosage 1008, a morningbasal dosage 1010 or a daytimebasal dosage 1012. In general, thebasal adaptivity mechanism 1006 looks at the currentmenstrual phase classification 1004 and the historical blood glucose concentration trends in earlier menstrual cycles to adapt the basal dosage amounts 1008, 1010 and 1012. In general, the dosages of basal insulin are increased in the earlyluteal phase 212 and gradually return to normal levels at the end of theluteal phase 204. The adaptation is tailored to the individual user based on learned patterns. Past bloodglucose concentration excursions 1002 are referenced in determining customized basal dosages. -
Figure 11A depicts aflowchart 1100 of illustrative steps that may be performed in exemplary embodiments forfollicular phase 202 adjustments. As noted above, decreases in insulin sensitivity are observed with some women in thefollicular phase 202. At 1102, the decreases in insulin sensitivity are determined. As mentioned above these decreases are determined by observation by themachine learning model 602. The basal insulin dosages are increased in the follicular phases to compensate for the decreased insulin sensitivity at 1104. -
Figure 11B depicts aflowchart 1110 of illustrative steps that may be performed in exemplary embodiments forluteal phase 204 adjustments. At 1112, a determination of increases in insulin sensitivity in theluteal phase 204 is determined. The basal insulin dosages for theluteal phase 204 are decreased in response at 1114. - Some examples help to illustrate the basal dosage adaptivity that may be provided. The adaptivity is customized to the particular user. Some women experience a reduction in insulin sensitivity of up to 25% in the early
luteal phase 212. Typical reductions of insulin sensitivity are in excess of 5%. In such instances, a nominal basal dosage would be set for the earlyfollicular phase 206, the mid-latefollicular phase 208 and theperi-ovulation phase 210. The basal dosage would be increased by 15% during the earlyluteal phase 212. The increase relative to the nominal basal dosage would be set at 10% in the midluteal phase 214 and would be set at a 5% increase relative to the nominal basal dosage in the lateluteal phase 216. - Some women may experience an increased insulin sensitivity in the
luteal phases luteal phase 214. For these women, there is a nominal basal dosage for thefollicular phase 202, theperi-ovulation phase 210 and the lateluteal phase 216. The basal dosage would be decreased by 5% relative to the nominal basal dosage in the earlyluteal phase 212 and would be decreased by 10% relative to the nominal basal dosage in the midluteal phase 214. - In some instances, no significant changes in insulin dosages for users are seen. The basal dosages are not adapted for such users.
- The bolus dosages may also be adapted.
Figure 12 depicts a diagram 120 showing illustrative inputs and outputs for abolus adaptivity mechanism 1202. Thebolus adaptivity mechanism 1202 may be realized as computer programming instructions in thecontrol application 116. Inputs to thebolus adaptivity mechanism 1202 may include the classification of the currentmenstrual cycle phase 1206 and the current blood glucose concentration reading along with information regarding blood glucose concentration excursions frompast cycles 1204. Thebolus adaptivity mechanism 1202 processes theseinputs bolus dosage amount 1208. Bolus dosages may be calculated when requested by theuser 108. -
Figure 13 depicts aflowchart 1300 of illustrative steps that may be performed in exemplary embodiments to generate an adapted insulin bolus dosage based on the current phase of the menstrual cycle of theuser 108. At 1302, theuser 108 requests a medicament bolus, such as a bolus of insulin. At 1304, the current phase of the menstrual cycle of theuser 108 is determined as discussed above. As was mentioned above, insulin sensitivity may vary with phase of the menstrual cycle. The exemplary embodiments may adapt for the changing insulin sensitivity by adapting the insulin to carbohydrates ratio (ICR), which may be used in determining the bolus dosage. The ICR is used to determine how much insulin is needed to compensate for a quantity of carbohydrates that is ingested. If insulin sensitivity increases, the ICR is decreased, whereas if insulin sensitivity decreases, the ICR is increased. At 1306, the ICR for the current phase of the menstrual cycle of theuser 108 is identified and at 1308 is used to calculate the bolus dosage. The magnitude of the increase in ICR or decrease in ICR is customized to the user's learned change in insulin sensitivity across the phases of the menstrual cycle of the user. - The bolus dosage is proportional to the carbohydrates ingested and the ICR. In particular, the bolus dosage equals the grams of carbohydrates ingested divided by the ICR. ICR typically will be higher during the
luteal phase 204 compared to thefollicular phase 202. A suitable increase in the ICR for the luteal phase is 10% compared to thefollicular phase 202. - The ICR adaptation may follow the insulin sensitivity trend. As explained above, the insulin sensitivity changes at the individual level. As an example, suppose that the insulin sensitivity decreases in the early
luteal phase 212 as described above, sensitivity changes the ICR would be reduced by 15% compared to baseline ICR in the earlyluteal phase 212, increased by 10% in the midluteal phase 214 and reduced by 5% in the lateluteal phase 216 compared to baseline ICR. - When the insulin sensitivity does not change through the menstrual cycle, the ICR may not be modulated through the menstrual period. The insulin sensitivity may be determined, such as described above, by looking at changes in blood glucose concentration for the user relative to the quantity of insulin delivered. If the area under the blood glucose curve is remaining the same, but the insulin delivery amount is increased, this means that the insulin sensitivity has been reduced (for the same blood sugar levels we are requiring more insulin). Conversely, if the area under the blood glucose curve remains the same, but the amount of insulin needed has reduced, then the insulin sensitivity has increased. When comparing insulin sensitivity across the menstrual cycle one can compare the ratio of blood sugar area under the curve to insulin delivery and infer insulin sensitivity variation or the lack thereof. If the change in insulin sensitivity over the user's menstrual cycle is below a threshold based on the comparison, the modulation by menstrual cycle phase described herein may not be performed.
- As was mentioned above, the
medicament delivery device 102 may include auser interface 117 and themanagement device 104 may include auser interface 123. Theuser interfaces Figure 14A , adisplay 1402 on a device 1400 (such as themedicament delivery device 102 or the management deice 104) may display a prompt 1406 for the user to verify and/or input the date that her last period began on.Buttons 1408 may be selected to verify (selecting "Y") or not verify (selecting "N") the displayed date. Buttons may be used to adjust the date rather than selecting a "Y" or "N" to verify the date. Thedisplay 1402 may also be used to verify a change in the basal dosage. As shown inFigure 14B , amessage 1410 that may be displayed ondisplay 1402 to prompt the user to accept or reject the proposed increase in basal dosage. A user interface screen or informational text may also be displayed to inform the user as to why an increase or decrease of X% (e.g., 10%) of the basal dosage is being recommended by the system.Buttons 1412 enable theuser 108 to accept or reject the proposed increase. Thedisplay 1402 may also display arequest 1414 to accept or reject a proposed reduction in ICR by choosingbuttons 1416 as shown inFigure 14C . A user interface screen or informational text may also be displayed to inform the user as to why an increase or decrease of the ICR (e.g., -15%) is being recommended by the system. Similarly, arequest 1418 to reduce or increase the ICR may be displayed on thedisplay 1402.Buttons 1420 enable the user to accept or reject the reduction. Such buttons, confirmations, recommendations, and/or informational text may be displayed and/or used throughout the menstrual cycle. - These are just a few examples of how the
user interface machine learning model 602. Other messages and graphical items may be displayed. -
Figure 15 shows anillustrative user interface 1500 for soliciting information from theuser 108. The user interface includes asection 1502 for obtaining information regarding the start date of the user's last period. Thesection 1502 includes acalendar 1504 that shows a month.Text 1506 identifies the month and year that is displayed. The current date is identified by ahighlight box 1508. An up arrow and adown arrow 1510 may be selected to choose the next month or the previous month, respectively. Theuser 108 simply clicks on the day of the month on which her last period started. This information is then recorded and stored, such as instorage 114. Theuser interface 1500 may also include atext box 1512 for theuser 108 to specify the number of days her period typically lasts. Theuser 108 may enter avalue 1514 in thetext box 1512 or may be select the+ button 1516 to increase the displayedvalue 1514 or the - button to decrease the displayed value by increments of 1. Atext box 1520 may be provided for theuser 108 to specify the average number of days in her menstrual cycle. Theuser 108 may enter avalue 1522 in thetext box 1520 or use the+ button 1524 and/or - button to select the correct value. The information gathered from the user may be stored instorage 114. This information may be used by the model 155 and thecontroller 110 as described above. - While the discussion has focused on exemplary embodiments, it should be appreciated that various changes in form and detail relative to the exemplary embodiments without departing from the intended scope of the appended claims.
- Although the present invention is defined in the attached claims, it should be understood that the present invention can also (alternatively) be defined in accordance with the following embodiments:
- 1. A method performed by a processor in an electronic device, comprising:
- receiving information regarding a menstrual cycle of a user; and
- based on the received information regarding a menstrual cycle of a user, adjusting a medicament dosage to be delivered by an automated medicament delivery device.
- 2. The method of
embodiment 1, wherein the received information is a current phase of a menstrual cycle of the user. - 3. The method of one of the preceding embodiments, wherein the received information is received from a machine learning model.
- 4. The method of one of the preceding embodiments, wherein the received information is information from which a current phase of the menstrual cycle is determined.
- 5. The method of one of the preceding embodiments, wherein the received information includes information from one or more sensors secured to the user.
- 6. The method of one of the preceding embodiments, wherein the medicament is one of insulin, glucagon or a glucagon peptide-1 (GLP-1) agonist.
- 7. The method of one of the preceding embodiments, wherein the adjusting comprises adjusting an insulin dosage to be delivered by the automated medicament delivery device based on an insulin sensitivity of the user for a current phase of the menstrual cycle of the user.
- 8. A method performed by a processor in an electronic device, comprising:
- receiving input from a sensor;
- based at least in part on the received input, determining with the processor a phase of a menstrual cycle of a user;
- determining insulin sensitivity of the user with the processor based on the determined phase of the menstrual cycle; and
- adjusting the insulin delivered by a delivery device based on the determined insulin sensitivity.
- 9. The method of
embodiment 8, wherein the sensor senses skin temperature, heart rate, skin conductance, or activity level. - 10. The method of one of
embodiments 8 to 9, wherein the method further comprises receiving additional inputs from multiple sensors and using the additional inputs in the determining of the phase of the menstrual cycle of the user. - 11. The method of one of
embodiments 8 to 10, wherein the additional inputs from the multiple sensors include a blood glucose concentration value for the user from a one of the sensors that is a glucose monitor. - 12. The method of one of
embodiments 8 to 11, wherein the adjusting the insulin to be delivered by a delivery device based on the determined insulin sensitivity comprises adjusting one of a basal insulin dosage or an insulin bolus dosage. - 13. The method of one of
embodiments 8 to 12, wherein the adjusting adjusts a size of a dosage of basal insulin to be delivered by the delivery device. - 14. The method of one of
embodiments 8 to 13, wherein the adjusting adjusts a size of dosage of an insulin bolus to be delivered by the delivery device. - 15. A method performed by a processor in an electronic device, comprising:
- with a machine learning model executing on the processor, learning patterns of medicament sensitivity of a user based on a phase of a menstrual cycle of a user;
- with the processor, adjusting delivery of medicament to the user based on the learned patterns to be delivered by a medicament delivery device to the user.
- 16. The method of
embodiment 15, further comprising:- receiving input from at least one sensor that senses information regarding the user; and
- processing the input to determine a current phase of the menstrual cycle of the user.
- 17. The method of one of
embodiments 15 to 16, wherein the input includes heart rate and skin temperature. - 18. The method of one of
embodiments 15 to 17, wherein the input includes blood glucose concentration and an indication of activity level. - 19. The method of one of
embodiments 15 to 18, wherein the learning comprises:- training on a data set derived from women other than the user; and
- subsequent to the training on the data set, training on data from the user to customize the machine learning model to the user.
- 20. The method of one of
embodiments 15 to 19, wherein the medicament is one of insulin, glucagon or a glucagon peptide-1 (GLP-1) agonist.
Claims (15)
- A method performed by a processor in an electronic device, comprising:receiving information regarding a menstrual cycle of a user; andbased on the received information regarding a menstrual cycle of a user, adjusting a medicament dosage to be delivered by an automated medicament delivery device.
- The method of claim 1, wherein the received information is a current phase of a menstrual cycle of the user.
- The method of one of the preceding claims, wherein the received information is received from a machine learning model.
- The method of one of the preceding claims, wherein the received information is information from which a current phase of the menstrual cycle is determined.
- The method of one of the preceding claims, wherein the received information includes information from one or more sensors secured to the user.
- The method of one of the preceding claims, wherein the medicament is one of insulin, glucagon or a glucagon peptide-1 (GLP-1) agonist.
- The method of one of the preceding claims, wherein the adjusting comprises adjusting an insulin dosage to be delivered by the automated medicament delivery device based on an insulin sensitivity of the user for a current phase of the menstrual cycle of the user.
- A method performed by a processor in an electronic device, comprising:receiving input from a sensor;based at least in part on the received input, determining with the processor a phase of a menstrual cycle of a user;determining insulin sensitivity of the user with the processor based on the determined phase of the menstrual cycle; andadjusting the insulin delivered by a delivery device based on the determined insulin sensitivity.
- The method of claim 8, wherein the sensor senses skin temperature, heart rate, skin conductance, or activity level.
- The method of one of claims 8 to 9 wherein the method further comprises receiving additional inputs from multiple sensors and using the additional inputs in the determining of the phase of the menstrual cycle of the user.
- The method of one of claims 8 to 10, wherein the additional inputs from the multiple sensors include a blood glucose concentration value for the user from a one of the sensors that is a glucose monitor.
- The method of one of claims 8 to 11, wherein the adjusting the insulin to be delivered by a delivery device based on the determined insulin sensitivity comprises adjusting one of a basal insulin dosage or an insulin bolus dosage.
- The method of one of claims 8 to 12, wherein the adjusting adjusts a size of a dosage of basal insulin to be delivered by the delivery device.
- The method of one of claims 8 to 13, wherein the adjusting adjusts a size of dosage of an insulin bolus to be delivered by the delivery device.
- A method performed by a processor in an electronic device, comprising:with a machine learning model executing on the processor, learning patterns of medicament sensitivity of a user based on a phase of a menstrual cycle of a user;with the processor, adjusting delivery of medicament to the user based on the learned patterns to be delivered by a medicament delivery device to the user.
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US202163216814P | 2021-06-30 | 2021-06-30 |
Publications (1)
Publication Number | Publication Date |
---|---|
EP4113527A1 true EP4113527A1 (en) | 2023-01-04 |
Family
ID=82492726
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP22181777.8A Pending EP4113527A1 (en) | 2021-06-30 | 2022-06-29 | Adjustment of medicament delivery by a medicament delivery device based on menstrual cycle phase |
Country Status (2)
Country | Link |
---|---|
US (1) | US20230001089A1 (en) |
EP (1) | EP4113527A1 (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100317952A1 (en) * | 2009-05-22 | 2010-12-16 | Abbott Diabetes Care Inc. | Methods for reducing false hypoglycemia alarm occurrence |
US20160066894A1 (en) * | 2014-03-21 | 2016-03-10 | Razzberry Inc. | Health state monitoring device |
US20170007214A1 (en) * | 2014-04-01 | 2017-01-12 | Koninklijke Philips N.V. | Unobtrusive ovulation tracking system and method using a subjects heart rate |
WO2021037724A1 (en) * | 2019-08-29 | 2021-03-04 | Ava Ag | System and method for determining time interval of fertility |
-
2022
- 2022-06-24 US US17/848,675 patent/US20230001089A1/en active Pending
- 2022-06-29 EP EP22181777.8A patent/EP4113527A1/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100317952A1 (en) * | 2009-05-22 | 2010-12-16 | Abbott Diabetes Care Inc. | Methods for reducing false hypoglycemia alarm occurrence |
US20160066894A1 (en) * | 2014-03-21 | 2016-03-10 | Razzberry Inc. | Health state monitoring device |
US20170007214A1 (en) * | 2014-04-01 | 2017-01-12 | Koninklijke Philips N.V. | Unobtrusive ovulation tracking system and method using a subjects heart rate |
WO2021037724A1 (en) * | 2019-08-29 | 2021-03-04 | Ava Ag | System and method for determining time interval of fertility |
Non-Patent Citations (2)
Title |
---|
ANONYMOUS: "PredictBGL User Manual", PREDICTBGL, 2 March 2018 (2018-03-02), XP055568862, Retrieved from the Internet <URL:https://web.archive.org/web/20180324182956/http://predictbgl.com:80/app_user_manual.pdf> [retrieved on 20190313] * |
TROUT K K ET AL: "INSULIN SENSITIVITY AND PREMENSTRUAL SYNDROME", CURRENT DIABETES REPORTS, CURRENT SCIENCE, PHILADELPHIA, VA, US, vol. 4, no. 4, 31 January 2004 (2004-01-31), pages 273 - 280, XP009053288, ISSN: 1534-4827 * |
Also Published As
Publication number | Publication date |
---|---|
US20230001089A1 (en) | 2023-01-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110869075B (en) | Calculation of residual insulin Activity content in Artificial islet systems | |
US11027063B2 (en) | Insulin delivery methods, systems and devices | |
US20090164251A1 (en) | Method and apparatus for providing treatment profile management | |
US20240009393A1 (en) | Blood glucose rate of change modulation of meal and correction insulin bolus quantity | |
US11986630B2 (en) | Dual hormone delivery system for reducing impending hypoglycemia and/or hyperglycemia risk | |
US20220379028A1 (en) | User parameter dependent cost function for personalized reduction of hypoglycemia and/or hyperglycemia in a closed loop artificial pancreas system | |
EP4113527A1 (en) | Adjustment of medicament delivery by a medicament delivery device based on menstrual cycle phase | |
US20220168506A1 (en) | Systems and methods for optimizing medicament dosing | |
US20240148971A1 (en) | Programmatic medicament titration with a medicament delivery device | |
US20230343430A1 (en) | Medicament adaptation and safety monitoring | |
US20230060939A1 (en) | Adjustment of insulin-to-carbohydrate ratio, correction factor, insulin dosage and timing of insulin delivery by a medicament delivery device | |
US20240066213A1 (en) | Techniques to increase rate of adaptivity for total daily insulin | |
US11738144B2 (en) | Techniques enabling adaptation of parameters in aid systems by user input | |
EP4120282A1 (en) | Techniques for recommending rescue carbohydrate ingestion in automatic medication delivery systems | |
AU2021219726B2 (en) | Personalized reduction of hypoglycemia and/or hyperglycemia in a closed loop system | |
EP4243030A1 (en) | Adjusting medicament delivery parameters in an open loop medicament delivery mode | |
US20230233762A1 (en) | User interface displays for assisting in medicament bolus calculation | |
US20220288311A1 (en) | Adaptive update of automatic insulin delivery (aid) control parameters | |
EP4254423A1 (en) | Autonomous adaptivity and set point control for a drug delivery device | |
WO2024059597A1 (en) | Incorporation of additional sensors into adaptation of aid systems |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
17P | Request for examination filed |
Effective date: 20220629 |
|
AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |